Upload with huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+license: apache-2.0
+tags:
+- canine
+- pretrained-on-english-language
+---
+
+### How to use
+
+Here is how to use this model:
+
+```python
+from transformers import CanineModel
+model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
+```

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 81.82,
+    "eval_accuracy_score": 0.9655789618614897,
+    "eval_f1": 0.8729121278140886,
+    "eval_loss": 0.2113661915063858,
+    "eval_precision": 0.8549075391180654,
+    "eval_recall": 0.8916913946587537,
+    "eval_runtime": 4.2063,
+    "eval_samples": 300,
+    "eval_samples_per_second": 71.322,
+    "eval_steps_per_second": 9.034,
+    "test_accuracy_score": 0.9729378934388994,
+    "test_f1": 0.8639598158225199,
+    "test_loss": 0.20872025191783905,
+    "test_precision": 0.8528925619834711,
+    "test_recall": 0.8753180661577609,
+    "test_runtime": 8.4194,
+    "test_samples": 604,
+    "test_samples_per_second": 71.739,
+    "test_steps_per_second": 9.027,
+    "train_loss": 0.015092053589997469,
+    "train_runtime": 8361.8493,
+    "train_samples": 2109,
+    "train_samples_per_second": 57.404,
+    "train_steps_per_second": 1.794
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ba4e271a8ad529bc9516fd1fcadd43b9f90e92fc6e1f2d06e4f83ec3b2c7e3
+size 709165101

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,409 @@
+{
+  "best_metric": 0.8729121278140886,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-swa/checkpoint-4000",
+  "epoch": 81.81818181818181,
+  "global_step": 5400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.03,
+      "eval_accuracy_score": 0.969571802285557,
+      "eval_f1": 0.8581610833927299,
+      "eval_loss": 0.11472320556640625,
+      "eval_precision": 0.8257887517146777,
+      "eval_recall": 0.8931750741839762,
+      "eval_runtime": 4.1914,
+      "eval_samples_per_second": 71.574,
+      "eval_steps_per_second": 9.066,
+      "step": 200
+    },
+    {
+      "epoch": 6.06,
+      "eval_accuracy_score": 0.9607600165220983,
+      "eval_f1": 0.8493342676944637,
+      "eval_loss": 0.14969909191131592,
+      "eval_precision": 0.8047808764940239,
+      "eval_recall": 0.8991097922848664,
+      "eval_runtime": 4.1964,
+      "eval_samples_per_second": 71.491,
+      "eval_steps_per_second": 9.055,
+      "step": 400
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.1339,
+      "step": 500
+    },
+    {
+      "epoch": 9.09,
+      "eval_accuracy_score": 0.9611730689797604,
+      "eval_f1": 0.8616039744499645,
+      "eval_loss": 0.16909180581569672,
+      "eval_precision": 0.8258503401360544,
+      "eval_recall": 0.900593471810089,
+      "eval_runtime": 4.1879,
+      "eval_samples_per_second": 71.635,
+      "eval_steps_per_second": 9.074,
+      "step": 600
+    },
+    {
+      "epoch": 12.12,
+      "eval_accuracy_score": 0.9651659094038276,
+      "eval_f1": 0.8659058487874465,
+      "eval_loss": 0.16794395446777344,
+      "eval_precision": 0.8337912087912088,
+      "eval_recall": 0.900593471810089,
+      "eval_runtime": 4.1904,
+      "eval_samples_per_second": 71.593,
+      "eval_steps_per_second": 9.068,
+      "step": 800
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0084,
+      "step": 1000
+    },
+    {
+      "epoch": 15.15,
+      "eval_accuracy_score": 0.9653035935563816,
+      "eval_f1": 0.8672817601135557,
+      "eval_loss": 0.1805761158466339,
+      "eval_precision": 0.8312925170068027,
+      "eval_recall": 0.9065281899109793,
+      "eval_runtime": 4.1859,
+      "eval_samples_per_second": 71.669,
+      "eval_steps_per_second": 9.078,
+      "step": 1000
+    },
+    {
+      "epoch": 18.18,
+      "eval_accuracy_score": 0.9566294919454771,
+      "eval_f1": 0.8536931818181818,
+      "eval_loss": 0.2617969214916229,
+      "eval_precision": 0.8188010899182562,
+      "eval_recall": 0.8916913946587537,
+      "eval_runtime": 4.1909,
+      "eval_samples_per_second": 71.583,
+      "eval_steps_per_second": 9.067,
+      "step": 1200
+    },
+    {
+      "epoch": 21.21,
+      "eval_accuracy_score": 0.9686080132176786,
+      "eval_f1": 0.873661670235546,
+      "eval_loss": 0.17235662043094635,
+      "eval_precision": 0.8418156808803301,
+      "eval_recall": 0.9080118694362018,
+      "eval_runtime": 4.1851,
+      "eval_samples_per_second": 71.683,
+      "eval_steps_per_second": 9.08,
+      "step": 1400
+    },
+    {
+      "epoch": 22.73,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0044,
+      "step": 1500
+    },
+    {
+      "epoch": 24.24,
+      "eval_accuracy_score": 0.9637890678782872,
+      "eval_f1": 0.875629043853343,
+      "eval_loss": 0.21507766842842102,
+      "eval_precision": 0.8493723849372385,
+      "eval_recall": 0.9035608308605341,
+      "eval_runtime": 4.1889,
+      "eval_samples_per_second": 71.619,
+      "eval_steps_per_second": 9.072,
+      "step": 1600
+    },
+    {
+      "epoch": 27.27,
+      "eval_accuracy_score": 0.9574555968608013,
+      "eval_f1": 0.8459900638750887,
+      "eval_loss": 0.24175740778446198,
+      "eval_precision": 0.8108843537414966,
+      "eval_recall": 0.884272997032641,
+      "eval_runtime": 4.1899,
+      "eval_samples_per_second": 71.601,
+      "eval_steps_per_second": 9.07,
+      "step": 1800
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.003,
+      "step": 2000
+    },
+    {
+      "epoch": 30.3,
+      "eval_accuracy_score": 0.9582817017761256,
+      "eval_f1": 0.8468085106382979,
+      "eval_loss": 0.25091126561164856,
+      "eval_precision": 0.811141304347826,
+      "eval_recall": 0.8857566765578635,
+      "eval_runtime": 4.1982,
+      "eval_samples_per_second": 71.459,
+      "eval_steps_per_second": 9.051,
+      "step": 2000
+    },
+    {
+      "epoch": 33.33,
+      "eval_accuracy_score": 0.9658543301665978,
+      "eval_f1": 0.8738284066330209,
+      "eval_loss": 0.225422665476799,
+      "eval_precision": 0.8499298737727911,
+      "eval_recall": 0.8991097922848664,
+      "eval_runtime": 4.2016,
+      "eval_samples_per_second": 71.402,
+      "eval_steps_per_second": 9.044,
+      "step": 2200
+    },
+    {
+      "epoch": 36.36,
+      "eval_accuracy_score": 0.9669558033870301,
+      "eval_f1": 0.8775216138328531,
+      "eval_loss": 0.22372400760650635,
+      "eval_precision": 0.8529411764705882,
+      "eval_recall": 0.9035608308605341,
+      "eval_runtime": 4.1974,
+      "eval_samples_per_second": 71.472,
+      "eval_steps_per_second": 9.053,
+      "step": 2400
+    },
+    {
+      "epoch": 37.88,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0024,
+      "step": 2500
+    },
+    {
+      "epoch": 39.39,
+      "eval_accuracy_score": 0.9611730689797604,
+      "eval_f1": 0.8640915593705293,
+      "eval_loss": 0.23863321542739868,
+      "eval_precision": 0.8342541436464088,
+      "eval_recall": 0.8961424332344213,
+      "eval_runtime": 4.1973,
+      "eval_samples_per_second": 71.474,
+      "eval_steps_per_second": 9.053,
+      "step": 2600
+    },
+    {
+      "epoch": 42.42,
+      "eval_accuracy_score": 0.9684703290651246,
+      "eval_f1": 0.8781542898341744,
+      "eval_loss": 0.1946461945772171,
+      "eval_precision": 0.8541374474053296,
+      "eval_recall": 0.9035608308605341,
+      "eval_runtime": 4.1975,
+      "eval_samples_per_second": 71.471,
+      "eval_steps_per_second": 9.053,
+      "step": 2800
+    },
+    {
+      "epoch": 45.45,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.003,
+      "step": 3000
+    },
+    {
+      "epoch": 45.45,
+      "eval_accuracy_score": 0.956354123640369,
+      "eval_f1": 0.845993031358885,
+      "eval_loss": 0.2664543688297272,
+      "eval_precision": 0.797634691195795,
+      "eval_recall": 0.900593471810089,
+      "eval_runtime": 4.1956,
+      "eval_samples_per_second": 71.503,
+      "eval_steps_per_second": 9.057,
+      "step": 3000
+    },
+    {
+      "epoch": 48.48,
+      "eval_accuracy_score": 0.9624122263527468,
+      "eval_f1": 0.8711303095752341,
+      "eval_loss": 0.2241496741771698,
+      "eval_precision": 0.8461538461538461,
+      "eval_recall": 0.8976261127596439,
+      "eval_runtime": 4.2045,
+      "eval_samples_per_second": 71.353,
+      "eval_steps_per_second": 9.038,
+      "step": 3200
+    },
+    {
+      "epoch": 51.52,
+      "eval_accuracy_score": 0.9617238055899766,
+      "eval_f1": 0.8640569395017793,
+      "eval_loss": 0.26432353258132935,
+      "eval_precision": 0.8303693570451436,
+      "eval_recall": 0.900593471810089,
+      "eval_runtime": 4.2012,
+      "eval_samples_per_second": 71.409,
+      "eval_steps_per_second": 9.045,
+      "step": 3400
+    },
+    {
+      "epoch": 53.03,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0017,
+      "step": 3500
+    },
+    {
+      "epoch": 54.55,
+      "eval_accuracy_score": 0.9681949607600165,
+      "eval_f1": 0.8776249094858798,
+      "eval_loss": 0.1974426507949829,
+      "eval_precision": 0.8571428571428571,
+      "eval_recall": 0.8991097922848664,
+      "eval_runtime": 4.1963,
+      "eval_samples_per_second": 71.491,
+      "eval_steps_per_second": 9.056,
+      "step": 3600
+    },
+    {
+      "epoch": 57.58,
+      "eval_accuracy_score": 0.9624122263527468,
+      "eval_f1": 0.8690563277249451,
+      "eval_loss": 0.25220534205436707,
+      "eval_precision": 0.8571428571428571,
+      "eval_recall": 0.8813056379821959,
+      "eval_runtime": 4.205,
+      "eval_samples_per_second": 71.343,
+      "eval_steps_per_second": 9.037,
+      "step": 3800
+    },
+    {
+      "epoch": 60.61,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.001,
+      "step": 4000
+    },
+    {
+      "epoch": 60.61,
+      "eval_accuracy_score": 0.9655789618614897,
+      "eval_f1": 0.8729121278140886,
+      "eval_loss": 0.2113661915063858,
+      "eval_precision": 0.8549075391180654,
+      "eval_recall": 0.8916913946587537,
+      "eval_runtime": 4.1875,
+      "eval_samples_per_second": 71.642,
+      "eval_steps_per_second": 9.075,
+      "step": 4000
+    },
+    {
+      "epoch": 63.64,
+      "eval_accuracy_score": 0.9625499105053008,
+      "eval_f1": 0.8552821997105645,
+      "eval_loss": 0.2266554832458496,
+      "eval_precision": 0.8347457627118644,
+      "eval_recall": 0.8768545994065282,
+      "eval_runtime": 4.1917,
+      "eval_samples_per_second": 71.57,
+      "eval_steps_per_second": 9.066,
+      "step": 4200
+    },
+    {
+      "epoch": 66.67,
+      "eval_accuracy_score": 0.969984854743219,
+      "eval_f1": 0.8743718592964824,
+      "eval_loss": 0.18208536505699158,
+      "eval_precision": 0.847009735744089,
+      "eval_recall": 0.9035608308605341,
+      "eval_runtime": 4.1915,
+      "eval_samples_per_second": 71.573,
+      "eval_steps_per_second": 9.066,
+      "step": 4400
+    },
+    {
+      "epoch": 68.18,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0021,
+      "step": 4500
+    },
+    {
+      "epoch": 69.7,
+      "eval_accuracy_score": 0.9551149662673826,
+      "eval_f1": 0.8406633020908435,
+      "eval_loss": 0.2883528769016266,
+      "eval_precision": 0.8176718092566619,
+      "eval_recall": 0.8649851632047477,
+      "eval_runtime": 4.1939,
+      "eval_samples_per_second": 71.533,
+      "eval_steps_per_second": 9.061,
+      "step": 4600
+    },
+    {
+      "epoch": 72.73,
+      "eval_accuracy_score": 0.9581440176235715,
+      "eval_f1": 0.8530050687907313,
+      "eval_loss": 0.2784726023674011,
+      "eval_precision": 0.8330975954738331,
+      "eval_recall": 0.8738872403560831,
+      "eval_runtime": 4.1999,
+      "eval_samples_per_second": 71.43,
+      "eval_steps_per_second": 9.048,
+      "step": 4800
+    },
+    {
+      "epoch": 75.76,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0017,
+      "step": 5000
+    },
+    {
+      "epoch": 75.76,
+      "eval_accuracy_score": 0.9633760154206251,
+      "eval_f1": 0.8614501076812634,
+      "eval_loss": 0.22903957962989807,
+      "eval_precision": 0.8344923504867872,
+      "eval_recall": 0.8902077151335311,
+      "eval_runtime": 59.3501,
+      "eval_samples_per_second": 5.055,
+      "eval_steps_per_second": 0.64,
+      "step": 5000
+    },
+    {
+      "epoch": 78.79,
+      "eval_accuracy_score": 0.9639267520308412,
+      "eval_f1": 0.8656499636891795,
+      "eval_loss": 0.24257344007492065,
+      "eval_precision": 0.8477951635846372,
+      "eval_recall": 0.884272997032641,
+      "eval_runtime": 4.1775,
+      "eval_samples_per_second": 71.814,
+      "eval_steps_per_second": 9.096,
+      "step": 5200
+    },
+    {
+      "epoch": 81.82,
+      "eval_accuracy_score": 0.9650282252512736,
+      "eval_f1": 0.868804664723032,
+      "eval_loss": 0.23794998228549957,
+      "eval_precision": 0.8538681948424068,
+      "eval_recall": 0.884272997032641,
+      "eval_runtime": 4.1803,
+      "eval_samples_per_second": 71.765,
+      "eval_steps_per_second": 9.09,
+      "step": 5400
+    },
+    {
+      "epoch": 81.82,
+      "step": 5400,
+      "total_flos": 2.254571897701939e+16,
+      "train_loss": 0.015092053589997469,
+      "train_runtime": 8361.8493,
+      "train_samples_per_second": 57.404,
+      "train_steps_per_second": 1.794
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 228,
+  "total_flos": 2.254571897701939e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ac6480402076c1686db3ef506cb31193ee138ab5a30c4309b85e194607585a
+size 3259